KaiquanMah
First Push
5c2271c
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.6819554567337036,
"min": 1.6819554567337036,
"max": 2.8632709980010986,
"count": 10
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 17187.90234375,
"min": 16364.80078125,
"max": 29354.25390625,
"count": 10
},
"SnowballTarget.Step.mean": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Step.sum": {
"value": 99960.0,
"min": 9952.0,
"max": 99960.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 8.809528350830078,
"min": 0.3549085259437561,
"max": 8.809528350830078,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 1797.143798828125,
"min": 68.85225677490234,
"max": 1797.143798828125,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 10
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06476696244105422,
"min": 0.06169447957026754,
"max": 0.07104881221255031,
"count": 10
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.3238348122052711,
"min": 0.24677791828107015,
"max": 0.3552440610627516,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.25020958155977957,
"min": 0.1391621481572442,
"max": 0.2798929020178084,
"count": 10
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 1.2510479077988979,
"min": 0.5566485926289768,
"max": 1.314935378565946,
"count": 10
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 1.6464094511999996e-05,
"min": 1.6464094511999996e-05,
"max": 0.000283764005412,
"count": 10
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 8.232047255999999e-05,
"min": 8.232047255999999e-05,
"max": 0.00127032007656,
"count": 10
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.105488,
"min": 0.105488,
"max": 0.194588,
"count": 10
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.52744,
"min": 0.4615520000000001,
"max": 0.92344,
"count": 10
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0002838512,
"min": 0.0002838512,
"max": 0.0047299412,
"count": 10
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.001419256,
"min": 0.001419256,
"max": 0.021179656,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 18.70909090909091,
"min": 4.045454545454546,
"max": 18.70909090909091,
"count": 10
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1029.0,
"min": 178.0,
"max": 1029.0,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 18.70909090909091,
"min": 4.045454545454546,
"max": 18.70909090909091,
"count": 10
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1029.0,
"min": 178.0,
"max": 1029.0,
"count": 10
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 10
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1685687645",
"python_version": "3.10.11 (main, Apr 5 2023, 14:15:10) [GCC 9.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "0.31.0.dev0",
"mlagents_envs_version": "0.31.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "1.11.0+cu102",
"numpy_version": "1.21.2",
"end_time_seconds": "1685687878"
},
"total": 232.66048185199998,
"count": 1,
"self": 0.43433527999991384,
"children": {
"run_training.setup": {
"total": 0.04111527500003831,
"count": 1,
"self": 0.04111527500003831
},
"TrainerController.start_learning": {
"total": 232.18503129700002,
"count": 1,
"self": 0.32242269399921497,
"children": {
"TrainerController._reset_env": {
"total": 3.745280651999792,
"count": 1,
"self": 3.745280651999792
},
"TrainerController.advance": {
"total": 227.98040313200113,
"count": 9137,
"self": 0.1354562989920396,
"children": {
"env_step": {
"total": 227.8449468330091,
"count": 9137,
"self": 166.34188825501724,
"children": {
"SubprocessEnvManager._take_step": {
"total": 61.365596656989055,
"count": 9137,
"self": 0.9644129949824674,
"children": {
"TorchPolicy.evaluate": {
"total": 60.40118366200659,
"count": 9137,
"self": 60.40118366200659
}
}
},
"workers": {
"total": 0.13746192100279586,
"count": 9137,
"self": 0.0,
"children": {
"worker_root": {
"total": 231.3148130210095,
"count": 9137,
"is_parallel": true,
"self": 109.08317839500887,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006018515000050684,
"count": 1,
"is_parallel": true,
"self": 0.004678994999949282,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0013395200001014018,
"count": 10,
"is_parallel": true,
"self": 0.0013395200001014018
}
}
},
"UnityEnvironment.step": {
"total": 0.03756950999991204,
"count": 1,
"is_parallel": true,
"self": 0.0004276600000139297,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00031696899986854987,
"count": 1,
"is_parallel": true,
"self": 0.00031696899986854987
},
"communicator.exchange": {
"total": 0.03502117399989402,
"count": 1,
"is_parallel": true,
"self": 0.03502117399989402
},
"steps_from_proto": {
"total": 0.001803707000135546,
"count": 1,
"is_parallel": true,
"self": 0.00035793800043393276,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0014457689997016132,
"count": 10,
"is_parallel": true,
"self": 0.0014457689997016132
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 122.23163462600064,
"count": 9136,
"is_parallel": true,
"self": 4.795277618991804,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 2.609895970993648,
"count": 9136,
"is_parallel": true,
"self": 2.609895970993648
},
"communicator.exchange": {
"total": 98.40547386201183,
"count": 9136,
"is_parallel": true,
"self": 98.40547386201183
},
"steps_from_proto": {
"total": 16.420987174003358,
"count": 9136,
"is_parallel": true,
"self": 3.189107430986496,
"children": {
"_process_rank_one_or_two_observation": {
"total": 13.231879743016862,
"count": 91360,
"is_parallel": true,
"self": 13.231879743016862
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00033108299999184965,
"count": 1,
"self": 0.00033108299999184965,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 226.39053460893592,
"count": 216365,
"is_parallel": true,
"self": 4.635124829899496,
"children": {
"process_trajectory": {
"total": 122.30200328003707,
"count": 216365,
"is_parallel": true,
"self": 121.34510694903724,
"children": {
"RLTrainer._checkpoint": {
"total": 0.9568963309998253,
"count": 2,
"is_parallel": true,
"self": 0.9568963309998253
}
}
},
"_update_policy": {
"total": 99.45340649899936,
"count": 45,
"is_parallel": true,
"self": 38.65857330199674,
"children": {
"TorchPPOOptimizer.update": {
"total": 60.79483319700262,
"count": 2289,
"is_parallel": true,
"self": 60.79483319700262
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.13659373599989522,
"count": 1,
"self": 0.0009706309999728546,
"children": {
"RLTrainer._checkpoint": {
"total": 0.13562310499992236,
"count": 1,
"self": 0.13562310499992236
}
}
}
}
}
}
}